Triple

T9047779
Position Surface form Disambiguated ID Type / Status
Subject Port of Felixstowe E216800 entity
Predicate nearbyCity P350 FINISHED
Object Harwich E143824 NE FINISHED

How this triple was built (2 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Harwich | Statement: [Port of Felixstowe, nearbyCity, Harwich]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Harwich
Context triple: [Port of Felixstowe, nearbyCity, Harwich]
  • A. Harwich chosen
    Harwich is a historic port town in Essex, England, which once served as a parliamentary borough represented in the British House of Commons.
  • B. Harwich
    Harwich is a coastal town on southeastern Cape Cod in Massachusetts known for its beaches, harbors, and summer tourism.
  • C. Felixstowe
    Felixstowe is a coastal town in Suffolk, England, best known for its major container port—one of the busiest in Europe—and its seaside resort.
  • D. Gosport
    Gosport is a coastal town and borough on the south coast of England, situated opposite Portsmouth Harbour in the county of Hampshire.
  • E. Lowestoft
    Lowestoft is a coastal town in Suffolk, England, known as the easternmost settlement in the United Kingdom and a traditional fishing and seaside resort.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69ca83d362e88190ae44b4e4dc194209 completed March 30, 2026, 2:08 p.m.
NER Named-entity recognition batch_69cc6b5022c88190ab6b6de3c3830a41 completed April 1, 2026, 12:48 a.m.
NED1 Entity disambiguation (via context triple) batch_69d0177fb9108190846fe872bb003b08 completed April 3, 2026, 7:39 p.m.
Created at: March 30, 2026, 7:09 p.m.